One of the most critical causes of colony collapse disorder in beekeeping is caused by the Varroa mite. This paper presents an embedded camera module supported by a deep learning algorithm for the process of early detecting of Varroa infestations. This is achieved using a deep learning algorithm that tries to identify bees inside the brood frames carrying the mite in real-time. The end-node device camera module is placed inside the brood box. It is equipped with offline detection in remote areas of limited network coverage or online imagery data transmission and mite detection over the cloud. The proposed deep learning algorithm uses a deep learning network for bee object detection and an image processing step to identify the mite on the previously detected objects. Finally, the authors present their proof of concept experimentation of their approach that can offer a total bee and varroa detection accuracy of close to 70%. The authors present in detail and discuss their experimental results.

This paper presents a bee-condition-monitoring system incorporated with a deep-learning process to detect bee swarming. This system includes easy-to-use image acquisition and various end node approaches for either on-site or cloud-based mechanisms. This system also incorporates a new smart CNN engine called Swarm-engine for detecting bees and the issue of notifications in cases of bee swarming conditions to the apiarists. First, this paper presents the authors’ proposed implementation system architecture and end node versions that put it to the test. Then, several pre-trained networks of the authors’ proposed CNN Swarm-engine were also validated to detect bee-clustering events that may lead to swarming. Finally, their accuracy and performance towards detection were evaluated using both cloud cores and embedded ARM devices on parts of the system’s different end-node implementations.

This paper proposes a holistic management and control system for the apiculture industry (Integrated Beekeeping System of holistic Management and Control – IBSMC). This integrated beehive array system mainly focuses on the regulation of bees living conditions, targeting both minimizing bee swarm mortality and maximizing productivity. Within the proposed IBSMC system architecture, additional security functionalities are implemented for bee monitoring, low energy consumption and incidents response. As a complete unit, the proposed IBSMC system is both a hive conditions monitoring and safety system. It communicates with the outer world using low power RF data transmission and the LoRaWAN transceivers. This paper presents the proposed IBSMC architecture consisting of new beehive cells embedded with functionalities for integrated conditions regulation and security provisions, as well as the communication protocols used for facility-conditions management, incidents’ acquisition and incidents’ response.

In viticulture, downy mildew is one of the most common diseases that, if not adequately treated, can diminish production yield. However, the uncontrolled use of pesticides to alleviate its occurrence can pose significant risks for farmers, consumers, and the environment. This paper presents a new framework for the early detection and estimation of the mildew’s appearance in viticulture fields. The framework utilizes a protocol for the real-time acquisition of drones’ high-resolution RGB images and a cloud-docker-based video or image inference process using object detection CNN models. The authors implemented their framework proposition using open-source tools and experimented with their proposed implementation on the debina grape variety in Zitsa, Greece, during downy mildew outbursts. The authors present evaluation results of deep learning Faster R-CNN object detection models trained on their downy mildew annotated dataset, using the different object classifiers of VGG16, ViTDet, MobileNetV3, EfficientNet, SqueezeNet, and ResNet. The authors compare Faster R-CNN and YOLO object detectors in terms of accuracy and speed. From their experimentation, the embedded device model ViTDet showed the worst accuracy results compared to the fast inferences of YOLOv8, while MobileNetV3 significantly outperformed YOLOv8 in terms of both accuracy and speed. Regarding cloud inferences, large ResNet models performed well in terms of accuracy, while YOLOv5 faster inferences presented significant object classification losses.

Modern irrigation systems utilize sensors and actuators, interconnected together as a single entity. In such entities, A.I. algorithms are implemented, which are responsible for the irrigation process. In this paper, the authors present an irrigation Open Watering System (OWS) architecture that spatially clusters the irrigation process into autonomous irrigation sections. Authors’ OWS implementation includes a Neuro-Fuzzy decision algorithm called FITRA, which originates from the Greek word for seed. In this paper, the FITRA algorithm is described in detail, as are experimentation results that indicate significant water conservations from the use of the FITRA algorithm. Furthermore, the authors propose a new communication protocol over LoRa radio as an alternative low-energy and long-range OWS clusters communication mechanism. The experimental scenarios confirm that the FITRA algorithm provides more efficient irrigation on clustered areas than existing non-clustered, time scheduled or threshold adaptive algorithms. This is due to the FITRA algorithm’s frequent monitoring of environmental conditions, fuzzy and neural network adaptation as well as adherence to past irrigation preferences.